A macOS menubar app that monitors LLM token throughput in real time. Tails log files from Claude Code and Codex, shows live tok/s on a tachometer gauge, tracks costs, and generates shareable stat cards.
A framework for managing AI model delegation in Claude Code. Two levers, fuel and throttle, control cost-quality tradeoff and parallelism for multi-agent orchestration.
Pick a time that works for you.
Tell me about your project and I'll get back to you soon.
